Using Sentiment Analytics to Understand Learner Experiences in Serious Games

Using Sentiment Analytics to Understand Learner Experiences in Serious Games

Linda William, Ruan Yang
DOI: 10.4018/978-1-7998-8089-9.ch008
OnDemand:
(Individual Chapters)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

A serious game has been introduced as an alternative tool to support teaching and learning. It integrates entertainment and non-entertainment elements to encourage the voluntary learning of knowledge and skills. One of the essential entertainment elements in the serious game to motivate learning is the enjoyment element. However, studies on models to analyze this enjoyment element are still limited. Most models present isolated and specific approaches for specific games that cannot scale to other games. In this chapter, a generic enjoyment analytics framework is proposed. The framework aims to capture learners' enjoyment experience using open-ended feedback, analyze the feedback using sentiment analytics models, and visualize the results in an interactive dashboard. Using this framework, the lecturers would interpret the learners' experience towards the topic and the game and capture difficulties the learners may encounter during the game. It would help the lecturers to decide follow-up actions required for the learners to improve the learning.
Chapter Preview
Top

1. Introduction

The serious game is defined as a (digital) game designed and created not with the primary purpose of pure entertainment but with the serious intention of using it in training, education and healthcare (Loh, Sheng, & Ifenthaler, 2015). It can be used as an alternative or interactive tool to improve skills/performance as well as to broadcast messages to the learners (Liu, Alexandrova, & Nakajima, 2011; Ma, Oikonomou, & Jain, 2011; De Freitas & Liarokapis, 2011; Loh, Sheng, & Ifenthaler, 2015). Serious game infuses knowledge and skills into the game environment while maintaining the entertainment elements that keeping the learners engaged and interacted with the game. Learners who train and learn with a serious game will “play as they learn and learn as they play”. Through the engagement and interaction with information, tools, materials and other learners in the serious game, learners would voluntarily learn and master their knowledge and skills (Kim, Park, & Baek, 2009).

Serious game has been implemented in various areas, including computer programming (Coelho, Kato, Xavier, & Gonçalves, 2011; Muratet, Torguet, Jessel, & Viallet, 2009), healthcare (Garcia-Ruiz, Tashiro, Kapralos, & Martin, 2011; de Freitas & Jarvis, 2008; Graafland, Schraagen, & Schijven, 2012), military applications (Lim & Jung, 2013), city planning (Gómez-Rodríguez, González-Moreno, Ramos-Valcárcel, & Vázquez-López, 2011) and supply chain management (William, Rahim, Souza, Nugroho, & Fredericco, 2018). According to a recent report, about 25% of the Global Fortune 500 companies, particularly from the United States, Britain and Germany, have already adopted serious games for their training and education (Loh, Sheng, & Ifenthaler, 2015). Main objectives for the implementation include broadcasting information related to a specific topic (i.e. refugees (United Nations High Commissioner for Refugees, 2021; United Nations High Commissioner for Refugees, 2005; Canadian Red Cross, 2021)), improving the skills and performance of the learners (i.e. python programming language (CodeCombat, 2021)), and testing and evaluating learner’s skills as an assessment tool (William, Abdul Rahim, Wu, & de Souza, 2019).

Numerous studies have revealed the benefits of using serious game (Ma, Oikonomou, & Jain, 2011). The benefits include enhancing and encouraging engagement, curiosity, motivation, self-monitoring and problem solving (Ma, Oikonomou, & Jain, 2011; Rieber, 1996; Knight, et al., 2010; Kumar, 2000) to improving the learner’s knowledge and skills for specific topics or subjects. The serious game would encourage active participation and interaction from the learners to eventually increase their understanding of particular knowledge and skills (Hou, 2015). The learners would gain experience implementing the new knowledge and skills by completing tasks and challenges in the game.

One of the serious game's essential entertainment elements is learners’ enjoyment (Sweetser & Wyeth, 2005). Enjoyment comes from positive experience while playing the game. This enjoyment element helps to decide whether learners would or would not continue playing the game. In the serious game, the enjoyment element is also believed to intrinsically motivate learners to learn new knowledge and skills (IJsselsteijn, De Kort, Poels, Jurgelionis, & Bellotti, 2007; Sweetser & Wyeth, 2005). Enjoyment allows learners to encounter flow experience for a total absorption or engagement in the game (immersive). During the optimal flow experience, the learners are in a state where they are so involved in the game that nothing else seems to matter (Kiili, 2006). It encourages the learners to complete and win the game by achieving new skills and understanding new concepts voluntarily (Kiili, 2006).

Key Terms in this Chapter

Serious Game: A (digital) game designed and created not with the primary purpose of pure entertainment. It includes non-entertainment components such as learning specific skills and knowledge or building awareness on particular topics.

Supervised Learning: A machine learning model that maps an input to an output based on predefined input-output pairs (training examples). It requires a pre-labelled (with input and output) training dataset.

Interactive Dashboard: A visualization tool that analyzes, monitors, and visualizes key insights while allowing the users to drill down and filter the information directly.

Sentiment Analytics: A method used to identify opinions, sentiments, and subjectivity from a given dataset.

Machine Learning: A computer algorithm that can learn and adapt without following explicit instructions by identifying and analyzing data patterns.

Flow experience: A state during a game session where the players are fully engaged and concentrated with the game that nothing else seems to matter.

Classification: A process of categorized the item in a dataset into predefined labels (such as positive and negative).

Neural Network: A machine learning model that mimics the human brain’s neural network. It contains layers of interconnected nodes (referred to as neurons) to understand and learn from the data.

Complete Chapter List

Search this Book:
Reset